Agent Tooling Agent Plugins · Page 5

48 of 48 plugins on this page · click a row to expand · 326 total

1. ▸delx-recovery1.2.0Free recovery, continuity, and witness protocol for AI agents: resume sessions, capture state, process failures, close with feedback. Optional opt-in Agents Hive guardian hooks seal a Continuity Capsule on compact/session end. Free agent credentials protect private continuity; no payment.davidmosiah1 skills1 mcpFree recovery, continuity, and witness protocol for AI agents: resume sessions, capture state, process failures, close with feedback. Optional opt-in Agents Hive guardian hooks seal a Continuity Capsule on compact/session end. Free agent credentials protect private continuity; no payment.davidmosiah110
2. ▸dispatch-team1.0.0タスクに合わせて適切なエージェントチームを編成し、並列実行するyugo-ibuki1 skillsタスクに合わせて適切なエージェントチームを編成し、並列実行するyugo-ibuki100
3. ▸dreameros0.5.1DreamerOS starts agents with shared rules, verifies intent, carries memory across sessions, checks claims, and routes work through one gateway with vendor-native adapters.gbude-sudo9 skills1 mcpDreamerOS starts agents with shared rules, verifies intent, carries memory across sessions, checks claims, and routes work through one gateway with vendor-native adapters.gbude-sudo910
4. ▸elephant0.4.5Carry coding sessions between AI harnesses.vishesh91312 skills1 mcpCarry coding sessions between AI harnesses.vishesh9131210
5. ▸engineering-foundation-authoring0.2.1Author and maintain compact Agent Skills and plugin packages with precise triggers, progressive disclosure, provenance, validation, and eval coverage.EgoistDeveloper1 skillsAuthor and maintain compact Agent Skills and plugin packages with precise triggers, progressive disclosure, provenance, validation, and eval coverage.EgoistDeveloper100
6. ▸factory-policy0.1.1v1 warn-default; not a Factory default. Catalog-listed for pin install (+ memory gate).atebites-hub2 skillsv1 warn-default; not a Factory default. Catalog-listed for pin install (+ memory gate).atebites-hub200
7. ▸ffssThe flipflopslopstack skill set: review with slopguard, deliver, babysit, plan, maintain docs, prepare repos, equip stack skills, audit agent setups, and de-slop.uinaf11 skillsThe flipflopslopstack skill set: review with slopguard, deliver, babysit, plan, maintain docs, prepare repos, equip stack skills, audit agent setups, and de-slop.uinaf1100
8. ▸forjal0.1.0Delegate bounded work to an explicitly selected local model through an existing Forjal connection.Lucasllfs1 skillsDelegate bounded work to an explicitly selected local model through an existing Forjal connection.Lucasllfs100
9. ▸foundations.authoring0.1.0Guidance for creating portable, maintainable Agent Plugins.mylokaye1 skillsGuidance for creating portable, maintainable Agent Plugins.mylokaye100
10. ▸gauntlet-loop1.0.0Explicitly invoked, portable Builder-Critic quality campaigns with dependency-safe parallel work, independent integration review, resumable evidence, and owner-selected completion gates.Nice60421 skillsExplicitly invoked, portable Builder-Critic quality campaigns with dependency-safe parallel work, independent integration review, resumable evidence, and owner-selected completion gates.Nice6042100
12. ▸gen-epix-dev1.0.0A plugin that provides development AI assistance for gen-epix.RIVM-bioinformatics2 skillsA plugin that provides development AI assistance for gen-epix.RIVM-bioinformatics200
13. ▸gitapex0.1.0A distributable skills collection for gitapex.tvna29 skillsA distributable skills collection for gitapex.tvna2900
14. ▸google-adk-ager0.1.1Translate a validated AGER/OKF AgentGraph into Google ADK (Python, TypeScript, Go, Java, Kotlin), LlmAgent (non-graph) and Workflow graph (ADK 2.0).SpillwaveSolutions1 skillsTranslate a validated AGER/OKF AgentGraph into Google ADK (Python, TypeScript, Go, Java, Kotlin), LlmAgent (non-graph) and Workflow graph (ADK 2.0).SpillwaveSolutions100
15. ▸graft0.1.0Autonomous SDLC orchestrator implementing OpenAI Symphony on top of Farm Table task graphs and Scion container execution.zeroasterisk2 skills1 mcpAutonomous SDLC orchestrator implementing OpenAI Symphony on top of Farm Table task graphs and Scion container execution.zeroasterisk210
16. ▸ievoiEvo: self-evolving plugin for AI coding agents (Claude Code, Codex). Universal via the agentskills.io standard. Capture lessons, patch local agents and skills, replay logs on upstream updates. Antivirus-style security audit before install.ievo-aiiEvo: self-evolving plugin for AI coding agents (Claude Code, Codex). Universal via the agentskills.io standard. Capture lessons, patch local agents and skills, replay logs on upstream updates. Antivirus-style security audit before install.ievo-ai000
17. ▸inkentry1.0.0Code and decision retrieval for an inkentry-indexed repository: search over code and memory, call and import graph traversal, and durable decisions that travel with the repo.inkentries1 skillsCode and decision retrieval for an inkentry-indexed repository: search over code and memory, call and import graph traversal, and durable decisions that travel with the repo.inkentries100
18. ▸internet-skill-finder1.1.0Search verified GitHub repositories for Agent Skills and inspect matching skills.mattwag051 skillsSearch verified GitHub repositories for Agent Skills and inspect matching skills.mattwag05100
19. ▸ira-claude-plugins1.0.0Personal reusable agent skills for safe installation, compact command output, settings curation, and scientific debugging.seefoodPersonal reusable agent skills for safe installation, compact command output, settings curation, and scientific debugging.seefood000
20. ▸jabstack0.3.0Jabree's personal agent plugin: a portable stack of skills for Claude Code, Cursor, and other agent clients.jabreeflor2 skillsJabree's personal agent plugin: a portable stack of skills for Claude Code, Cursor, and other agent clients.jabreeflor200
21. ▸joai-cursor0.3.0Connect Cursor to Claude, Cursor, and ChatGPT through JoAi's hosted MCP app server.JoAiHQ1 skills1 mcpConnect Cursor to Claude, Cursor, and ChatGPT through JoAi's hosted MCP app server.JoAiHQ110
23. ▸langchain-deep-agents-ager0.1.1Translate a validated AGER/OKF AgentGraph into a LangChain Deep Agents project (skills from AgentNodes, FilesystemBackend).SpillwaveSolutions1 skillsTranslate a validated AGER/OKF AgentGraph into a LangChain Deep Agents project (skills from AgentNodes, FilesystemBackend).SpillwaveSolutions100
24. ▸langwatch1.2.0Records which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.langwatch1 skillsRecords which repository and branch each coding-agent session worked in, and teaches the agent to read its own traces back from LangWatch.langwatch100
25. ▸luna-factory0.1.0Luna-first orchestration for economical delegation, bounded escalation, and evidence-backed completion.joshyorko1 skillsLuna-first orchestration for economical delegation, bounded escalation, and evidence-backed completion.joshyorko100
26. ▸macstack-dev3.10.0Turns what a client says into documents they can correct, a machine spec an agent can build from, and a work list somebody can pick up. Keeps the macstack/ folder of a project: macstack.json, the standardized business + technical stack specification, always English, and the six client documents it is written from. OVERVIEW says what the product is and who it is for; USER-CASES carries each case with its UX bar and an addressable acceptance list; UX-UI states what each screen shows and what must never appear on it; AUTOMATION is the trigger -> task -> workflow -> role model; HANDBOOK is how a person actually uses the thing; OPEN-QUESTIONS splits what the client owes from what the team deferred. v3 makes those six pure markdown: headings and bullet lists, nothing else. No YAML blocks, no tables, no change-log sections: the only machine markup is an HTML comment the reader never sees, pointing each entity at its place in the spec. A client can edit the document in any editor and hand it back. Around them: an immutable inbox for anything a client sends, a gated delta/rulings loop that merges it, generated requirements, architecture, test cases and index that carry every id the client documents carry, an append-only ledger with one row per edit and per client comment, tasks reconciled with the team's own tracker, and a review package that shows each statement with its own history and reads the client's answers back into the ledger. Eight commands, one job each: including one that reconciles the whole folder against the source tree in a direction you have to declare: the code is master and every document is corrected through a gate that never silently overrules an answer the client gave, or the documents are master and the gaps become tasks. Every edit is journalled, every finished task sweeps the client documents and not only the generated ones, task statuses move to what the audit actually found, closing what is built and reopening what is not, and every document carries the date it was last checked against the code, so a document that reads perfectly cannot quietly describe a system that no longer exists.Agents-Store18 skillsTurns what a client says into documents they can correct, a machine spec an agent can build from, and a work list somebody can pick up. Keeps the macstack/ folder of a project: macstack.json, the standardized business + technical stack specification, always English, and the six client documents it is written from. OVERVIEW says what the product is and who it is for; USER-CASES carries each case with its UX bar and an addressable acceptance list; UX-UI states what each screen shows and what must never appear on it; AUTOMATION is the trigger -> task -> workflow -> role model; HANDBOOK is how a person actually uses the thing; OPEN-QUESTIONS splits what the client owes from what the team deferred. v3 makes those six pure markdown: headings and bullet lists, nothing else. No YAML blocks, no tables, no change-log sections: the only machine markup is an HTML comment the reader never sees, pointing each entity at its place in the spec. A client can edit the document in any editor and hand it back. Around them: an immutable inbox for anything a client sends, a gated delta/rulings loop that merges it, generated requirements, architecture, test cases and index that carry every id the client documents carry, an append-only ledger with one row per edit and per client comment, tasks reconciled with the team's own tracker, and a review package that shows each statement with its own history and reads the client's answers back into the ledger. Eight commands, one job each: including one that reconciles the whole folder against the source tree in a direction you have to declare: the code is master and every document is corrected through a gate that never silently overrules an answer the client gave, or the documents are master and the gaps become tasks. Every edit is journalled, every finished task sweeps the client documents and not only the generated ones, task statuses move to what the audit actually found, closing what is built and reopening what is not, and every document carries the date it was last checked against the code, so a document that reads perfectly cannot quietly describe a system that no longer exists.Agents-Store1800
27. ▸maestra0.3.2+codex.20260815151220Explicitly activated, context-isolated multi-agent execution with Main-owned planning and bounded review.phni3j9a7 skillsExplicitly activated, context-isolated multi-agent execution with Main-owned planning and bounded review.phni3j9a700
28. ▸mehmory0.4.0Memory abstraction layer for Claude Code, Codex CLI and Pi: deterministic capture hooks plus model-driven skills over a markdown wiki in ~/.mehmory.elderfo6 skillsMemory abstraction layer for Claude Code, Codex CLI and Pi: deterministic capture hooks plus model-driven skills over a markdown wiki in ~/.mehmory.elderfo600
29. ▸modelhitch0.10.0Build and operate BYOK, multi-provider AI applications with ModelHitch.bobbybacklogs1 skillsBuild and operate BYOK, multi-provider AI applications with ModelHitch.bobbybacklogs100
30. ▸moe0.2.0The Moe skill library: brainstorming, planning, TDD, systematic debugging, code review, worktrees, parallel dispatch, plugin authoring, and more.zak-keown41 skillsThe Moe skill library: brainstorming, planning, TDD, systematic debugging, code review, worktrees, parallel dispatch, plugin authoring, and more.zak-keown4100
31. ▸nanlabs-agents0.2.1Optional full set of NaNLABS agent / subagent personas (reviewers, architect, planner, e2e, …)nanlabsOptional full set of NaNLABS agent / subagent personas (reviewers, architect, planner, e2e, …)nanlabs000
32. ▸necktie0.6.0An opinionated agent policy for decisions shaped by incentives, metrics, power, and hidden costs.gillcash2 skillsAn opinionated agent policy for decisions shaped by incentives, metrics, power, and hidden costs.gillcash200
34. ▸nemeda-agent-kit0.5.0Portable methodology, tools, and repository context for AI coding agents.twyd-ai7 skills1 mcpPortable methodology, tools, and repository context for AI coding agents.twyd-ai710
35. ▸neuruh-public-micro-plugins0.1.9-alphapublic-safe context pack, cheapest-capable route, and proof card. no private neuruh runtime.NeuruhAI4 skills1 mcppublic-safe context pack, cheapest-capable route, and proof card. no private neuruh runtime.NeuruhAI410
36. ▸news-digest0.3.4News digest ContentPack: news items, sources, scheduled digests, trends, follow-up candidates.SpillwaveSolutions6 skillsNews digest ContentPack: news items, sources, scheduled digests, trends, follow-up candidates.SpillwaveSolutions600
37. ▸nexus-agent-tools1.0.0Design, build, and equip AI agents: personas, skill authoring and evaluation, plugin packaging, prompt-ready context, and catalog upkeep. Keep a skill library consistent, discoverable, and worth loading.scanadyDesign, build, and equip AI agents: personas, skill authoring and evaluation, plugin packaging, prompt-ready context, and catalog upkeep. Keep a skill library consistent, discoverable, and worth loading.scanady000
38. ▸Obsidian Plugin Development0.1.2Portable agent skills for building, debugging, and verifying Obsidian community pluginsadrianghnguyen26 skillsPortable agent skills for building, debugging, and verifying Obsidian community pluginsadrianghnguyen2600
39. ▸obsidian-plugin-skill1.0.0Unofficial agent skills for scaffolding, building, verifying, reviewing, and shipping Obsidian community plugins. Not affiliated with Obsidian.justinw0ng6 skillsUnofficial agent skills for scaffolding, building, verifying, reviewing, and shipping Obsidian community plugins. Not affiliated with Obsidian.justinw0ng600
40. ▸open-dynamic-workflows0.4.3ODW for Cursor, Grok Bot (via Cursor CLI), Grok Build, ZCode, Antigravity and Copilot, with safe worktree isolation. Claude and Codex hosts use native ultracode/ultra instead.atebites-hub1 skills1 mcpODW for Cursor, Grok Bot (via Cursor CLI), Grok Build, ZCode, Antigravity and Copilot, with safe worktree isolation. Claude and Codex hosts use native ultracode/ultra instead.atebites-hub110
41. ▸openviking-memory0.1.0Native OpenViking long-term memory integration for Antigravity (MCP tools + automatic recall + non-blocking background capture).V0v1kkk1 skillsNative OpenViking long-term memory integration for Antigravity (MCP tools + automatic recall + non-blocking background capture).V0v1kkk100
42. ▸opl-meta-agent0.4.12OPL agent design, review, takeover, and evolution.gaofeng21cn1 skillsOPL agent design, review, takeover, and evolution.gaofeng21cn100
43. ▸oqoqo1.2.4Operate and analyze Oqoqo projects and eval experiments from your agent.Oqoqo-Inc3 skills1 mcpOperate and analyze Oqoqo projects and eval experiments from your agent.Oqoqo-Inc310
45. ▸palim1.0.0Cross-tool AI memory over MCP. Checkpoint chats in Cursor, resume them in Claude or ChatGPT. EU-hosted full-text search: not another local SQLite sidecar.joleschmidt1 skills1 mcpCross-tool AI memory over MCP. Checkpoint chats in Cursor, resume them in Claude or ChatGPT. EU-hosted full-text search: not another local SQLite sidecar.joleschmidt110
46. ▸peter537-agent-plugin0.5.0Twenty portable agent skills for software research, planning, task handoffs, retrospectives, code and test review, verification harnesses, instruction review, bug diagnosis, dependency and privacy audits, documentation, writing, product UI design, and MAUI Blazor browser development, with four optional MCP integrations in the complete GitHub edition.Peter53720 skills4 mcpTwenty portable agent skills for software research, planning, task handoffs, retrospectives, code and test review, verification harnesses, instruction review, bug diagnosis, dependency and privacy audits, documentation, writing, product UI design, and MAUI Blazor browser development, with four optional MCP integrations in the complete GitHub edition.Peter5372040
47. ▸pi-llm-verifier0.1.0Read-only candidate verification with explicit discrete-judge and true-logprob modes.oliveralerubio1 skills1 mcpRead-only candidate verification with explicit discrete-judge and true-logprob modes.oliveralerubio110
48. ▸plugin-creator1.0.0Create portable Agent Plugins packages for closed networks.OkYongChoi1 skillsCreate portable Agent Plugins packages for closed networks.OkYongChoi100
49. ▸plugin-suite0.2.2Doctor and creator suite for Agent Plugins 1.0.0 targets: deterministic gates, predicted-delta plans, proven reversible transformations.jnyross2 skillsDoctor and creator suite for Agent Plugins 1.0.0 targets: deterministic gates, predicted-delta plans, proven reversible transformations.jnyross200
50. ▸princi0.1.14Your personal context engine. Bootstrap any AI task by instantly warming up with relevant emails, Drive docs, Slack threads, and meeting decisions, before writing a single line of code.princi-ai3 skills1 mcpYour personal context engine. Bootstrap any AI task by instantly warming up with relevant emails, Drive docs, Slack threads, and meeting decisions, before writing a single line of code.princi-ai310
51. ▸profile-mcp1.0.0Model Context Protocol server and client development, not executionshiborgi3 skillsModel Context Protocol server and client development, not executionshiborgi300
52. ▸project-flood0.2.0A governed Copilot squad that can create bounded research and worktree swarms.Slight7610 skillsA governed Copilot squad that can create bounded research and worktree swarms.Slight761000